International Journal of Information Technology & Decision Making

Tornado prediction variables are analyzed using machine learning and decision analysis techniques. A model based on several choice procedures and the superposition principle is applied for different methods of data analysis. The constructed model has been tested on a database of tornadic events. It is shown that the tornado prediction model developed herein is more efficient than a previous set of machine learning models, opening the way to more accurate decisions.

Recently, the number of deteriorating bridges has drastically increased. Furthermore, tight maintenance budgets are cut down, imposing escalating adverse implications on the safety of bridges. This state of affairs entails the development of decision support systems for the effective management of bridges within the allocated budget. As such, this study introduces an invasive weed optimization-based fuzzy decision-making framework designated for bridge intervention prioritization in both element and network levels. The proposed decision-making platform encompasses three main tiers. The first tier is an optimized fuzzy analytical network process model that aims at computing the weighting vector of the bridge defects, namely corrosion, delamination, cracking, spalling and scaling. In this model, a genetic algorithm optimization model is formulated to improve the consistencies of judgment matrices through circumventing the imprecisions encountered by the classical judgment assignment. The second tier encompasses establishing an integrated bridge deck condition assessment model capitalizing on ground-penetrating radar and inspection reports. In it, the severities of the bridge defects are demonstrated in the form of fuzzy membership functions to address the inherent uncertainties of inspection. Subsequently, a variable-length invasive weed optimization model is structured to automatically calibrate the fuzzy membership functions. The third model is designed for structuring a bridge maintenance decision-making strategy stepping on the integrated condition index. The capabilities of the proposed framework were validated through several levels of comparisons. For instance, it significantly outperformed some of the current condition assessment models. Additionally, it inferred that the thresholds separating the four categories of the integrated bridge deck condition index are 75.651, 67.769 and 60.318.

Coronavirus disease (COVID-19) pandemic has a tremendous effect on people’s lives worldwide, and the number of infected patients increases daily. The healthcare sector is affected by a large number of patients with COVID-19, and a solution is urgently needed to avert the risk of deteriorating patients in terms of prioritizing patients based on their health conditions. Prioritization of patients with COVID-19 is a complex and multi-criteria decision-analysis (MCDA) problem due to (i) multiple biological laboratory examination criteria, (ii) criteria importance and (iii) trade-off amongst the criteria. This study presents a new multi-biological laboratory examination framework for prioritizing patients with COVID-19 on the basis of integrated MCDA methods. The experiment was conducted on the basis of three phases. In the first phase, patient datasets containing eight biological laboratory examination criteria for six patients with COVID-19 were derived and discussed. The outcome of this phase was used to propose a decision matrix on the basis of the intersection between “biological laboratory examination criteria” and “COVID-19 patients list”. In the second phase, the analytic hierarchy process (AHP) method was utilized to set the subjective weights for the biological laboratory examination criteria by respiratory experts. In the last phase, the VIekriterijumsko KOmpromisno Rangiranje (VIKOR) method was adopted to prioritize patients in the context of individual and group decision making (GDM). Results showed that (1) the integration of AHP–VIKOR method based on individual and GDM contexts was effective for solving prioritization problems for patients with COVID-19, and (2) the prioritization results of patients with COVID-19 showed no variation in the internal and external VIKOR GDM contexts. The proposed multi-biological laboratory examination framework can differentiate between the mild and serious or critical condition of patients with COVID-19 by prioritizing them based on integrated AHP–VIKOR methods. In conclusion, medical sectors can use the proposed framework to differentiate the health conditions of infected patients and to assign appropriate care with prompt and effective treatment.

In this paper, a novel approach and framework based on interval-dependent degree and probability distribution for multi-criteria decision-making problems with multi-valued neutrosophic sets (MVNSs) is proposed. First, a simplified dependent function and distribution function are given and integrated into a concise formula, which is called the interval-dependent function and contains interval computing and probability distribution information in an interval. Then a transformation operator is defined and it is shown how to convert MVNSs into an interval set. Subsequently, the interval-dependent function with the probability distribution of MVNSs is deduced. Finally, an example and comparative analysis are provided to verify the feasibility and effectiveness of the proposed method. In addition, uncertainty analysis, which reflects the dynamic change of the ranking result with decision-makers’ preferences, is performed by setting different distribution functions, which increases the reliability and accuracy of the proposed method.

To mitigate the acute water shortage problems, water utilities are combating to find potential solutions. Water losses management in Water Supply Networks (WSNs) is amongst the prominent solutions. This work intends to develop a decision support framework to diagnose the criticality of WSNs according to an associated Water Loss Risk Index (WLRI) at pipe and zone levels. It utilized the Fuzzy Analytic Hierarchy Process (FAHP) to evaluate the influential factors that contribute to water losses. The Fuzzy Synthetic Evaluation Technique (FSET) has been utilized to assess WLRI at pipe level and Ordered Weighted Averaging (OWA) operator has been used to aggregate the individual WLRI values for each zone. The framework is extended by incorporating Monte Carlo simulation model to generate the final ranking of zones. The outcomes of this simulation showed fair stability in terms of ranking the scrutinized zones. The integration of this framework in water losses management practices and planning policies of water utilities has a large potential in improving water supply services and the performance of WSNs.

Projects are, by definition, risky and uncertain ventures. Therefore, the performance and risk of major projects should be carefully controlled in order to increase their probability of success. Quantitative project control techniques assist project managers in detecting problems, thus responding to them early on, by comparing the baseline plan with the project progress. However, project risk and uncertainty are rarely considered by these techniques. This paper proposes a project control framework that integrates the project uncertainty and associated risk factors into project control. Our framework is based on earned value management (EVM), which is an effective and widely used quantitative project control technique. The framework uses hybrid Bayesian Networks (BNs) to enhance EVM with the ability to compute the uncertainty associated with its parameters and risk factors. The framework can be applied to projects from different domains, and we illustrate its use with a simple example and a case study of a construction project.

Probability multi-valued neutrosophic set (PMVNS) is a preferable tool to capture the preference and hesitancy of decision makers (DMs) and to depict inconsistent and ambiguous information. In this paper, we improve the multi-attributive border approximation area comparison (MABAC) method under the PMVNS environment and establish a three-phase multi-attribute group decision-making (MAGDM) method. Firstly, some concepts of PMVNS, traditional MABAC method and regret theory (RT) are reviewed. Then, the similarity measure for PMVNSs is defined and utilized to derive the important degree of DMs, and the likelihood of preference relations expressed by the probability multi-valued neutrosophic numbers (PMVNNs) is first presented and employed to replace the distance deviation in traditional MABAC method. Furthermore, a novel MAGDM method where the performance of alternatives is expressed by the PMVNN is established by combining the likelihood-based MABAC method and RT which considered given DMs’ behavior psychology. Finally, a case study is implemented to demonstrate the feasibility and applicability of our proposed approach.

A review of modern methods of data normalization in the tasks of multicriteria decision-making and multidimensional classification is presented. The invariant properties of linear normalization methods are determined. Two basic principles of normalization of multidimensional data are defined: preservation of dispositions of natural and normalized values on the measurement scale and the absence of a displacement in the areas of normalized values of various criteria relative to each other. A method is proposed for converting normalized values of cost criteria to profit criteria based on the reverse sorting algorithm (ReS-algorithm). The ReS-algorithm preserves the dispositions of the natural and normalized values of the attributes of the alternatives and eliminates the displacement the areas of normalized values of the cost criteria relative to the profit criteria, which ensures the equality of the contributions of various criteria to the performance indicator of the alternatives.